| | |
|---|
| | | |
|---|
| | | Step 1) Prepare server environment (on server). |
|---|
| | | ``` |
|---|
| | | #Optional, modelscope cuda docker is preferred. |
|---|
| | | docker run --network host -d -it --gpus '"device=0"' -v /data:/data registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-cuda11.3.0-py37-torch1.11.0-tf1.15.5-1.2.0 |
|---|
| | | # Install modelscope and funasr, or install with modelscope cuda-docker image. |
|---|
| | | |
|---|
| | | # Get into grpc directory. |
|---|
| | | cd /opt/conda/lib/python3.7/site-packages/funasr/runtime/python/grpc |
|---|
| | | ``` |
|---|
| | | |
|---|
| | | |
|---|
| | | Step 2) Generate protobuf file (for server and client). |
|---|
| | | ``` |
|---|
| | | #Optional, paraformer_pb2.py and paraformer_pb2_grpc.py are already generated. |
|---|
| | | # Optional, paraformer_pb2.py and paraformer_pb2_grpc.py are already generated. |
|---|
| | | python -m grpc_tools.protoc --proto_path=./proto -I ./proto --python_out=. --grpc_python_out=./ ./proto/paraformer.proto |
|---|
| | | ``` |
|---|
| | | |
|---|
| | |
|---|
| | | |
|---|
| | | Step 4) Start grpc client (on client with microphone). |
|---|
| | | ``` |
|---|
| | | #Install dependency. |
|---|
| | | # Install dependency. Optional. |
|---|
| | | python -m pip install pyaudio webrtcvad |
|---|
| | | ``` |
|---|
| | | ``` |
|---|
| | | #Start client. |
|---|
| | | # Start client. |
|---|
| | | python grpc_main_client_mic.py --host 127.0.0.1 --port 10095 |
|---|
| | | ``` |
|---|
| | | |
|---|
| | |
|---|
| | | |
|---|
| | | |
|---|
| | | ## Reference |
|---|
| | | We borrow or refer to some code from: |
|---|
| | | We borrow from or refer to some code as: |
|---|
| | | |
|---|
| | | 1)https://github.com/wenet-e2e/wenet/tree/main/runtime/core/grpc |
|---|
| | | |
|---|
